-- |
-- Module       : Data.Text.Lazy.Encoding.Base16
-- Copyright    : (c) 2020-2026 Emily Pillmore
-- License      : BSD-style
--
-- Maintainer   : Emily Pillmore <emilypi@cohomolo.gy>
-- Stability    : stable
-- Portability  : non-portable
--
-- This module contains 'Data.Text.Lazy.Text'-valued combinators for
-- implementing the RFC 4648 specification of the Base16
-- encoding format. This includes lenient decoding variants, as well as
-- internal and external validation for canonicity.
--
module Data.Text.Lazy.Encoding.Base16
( encodeBase16
, decodeBase16
, decodeBase16Untyped
, decodeBase16With
, decodeBase16Lenient
, parseBase16
) where


import Data.Base16.Types
import Data.Bifunctor (first)
import Data.ByteString.Lazy (ByteString)
import qualified Data.ByteString.Lazy.Base16 as B16L
import Data.Char (chr)
import qualified Data.Text as T
import Data.Text.Encoding.Base16.Error (Base16Error(..))
import Data.Text.Lazy (Text)
import qualified Data.Text.Lazy.Encoding as TL

-- $setup
--
-- >>> import Data.Base16.Types
-- >>> :set -XOverloadedStrings
--

-- | Encode a lazy 'Text' value in Base16.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
-- === __Examples__:
--
-- >>> encodeBase16 "Sun"
-- "53756e"
--
encodeBase16 :: Text -> Base16 Text
encodeBase16 :: Text -> Base16 Text
encodeBase16 = ByteString -> Base16 Text
B16L.encodeBase16 (ByteString -> Base16 Text)
-> (Text -> ByteString) -> Text -> Base16 Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE encodeBase16 #-}

-- | Decode a Base16-encoded lazy 'Text' value.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
-- === __Examples__:
--
-- >>> decodeBase16 $ assertBase16 "53756e"
-- "Sun"
--
decodeBase16 :: Base16 Text -> Text
decodeBase16 :: Base16 Text -> Text
decodeBase16 = ByteString -> Text
TL.decodeUtf8 (ByteString -> Text)
-> (Base16 Text -> ByteString) -> Base16 Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Base16 ByteString -> ByteString
B16L.decodeBase16 (Base16 ByteString -> ByteString)
-> (Base16 Text -> Base16 ByteString) -> Base16 Text -> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. (Text -> ByteString) -> Base16 Text -> Base16 ByteString
forall a b. (a -> b) -> Base16 a -> Base16 b
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase16 #-}

-- | Decode an untyped Base16-encoded lazy 'Text' value.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
-- === __Examples__:
--
-- >>> decodeBase16Untyped "53756e"
-- Right "Sun"
--
-- >>> decodeBase16Untyped "6x"
-- Left "invalid character at offset: 1"
--
decodeBase16Untyped :: Text -> Either T.Text Text
decodeBase16Untyped :: Text -> Either Text Text
decodeBase16Untyped = (ByteString -> Text) -> Either Text ByteString -> Either Text Text
forall a b. (a -> b) -> Either Text a -> Either Text b
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap ByteString -> Text
TL.decodeUtf8 (Either Text ByteString -> Either Text Text)
-> (Text -> Either Text ByteString) -> Text -> Either Text Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> Either Text ByteString
B16L.decodeBase16Untyped (ByteString -> Either Text ByteString)
-> (Text -> ByteString) -> Text -> Either Text ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase16Untyped #-}

-- | Attempt to decode an untyped lazy 'Text' value as Base16, converting from
-- 'ByteString' to 'Text' according to some encoding function. In practice,
-- This is something like 'decodeUtf8'', which may produce an error.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
-- @
-- 'decodeBase16With' 'TL.decodeUtf8''
--   :: 'ByteString' -> 'Either' ('Base16Error' 'UnicodeException') 'Text'
-- @
--
-- @since 0.3.0.0
--
decodeBase16With
    :: (ByteString -> Either err Text)
      -- ^ convert a bytestring to text (e.g. 'T.decodeUtf8'')
    -> ByteString
      -- ^ Input to decode
    -> Either (Base16Error err) Text
decodeBase16With :: forall err.
(ByteString -> Either err Text)
-> ByteString -> Either (Base16Error err) Text
decodeBase16With ByteString -> Either err Text
f ByteString
t = case ByteString -> Either Text ByteString
B16L.decodeBase16Untyped ByteString
t of
    Left Text
de -> Base16Error err -> Either (Base16Error err) Text
forall a b. a -> Either a b
Left (Base16Error err -> Either (Base16Error err) Text)
-> Base16Error err -> Either (Base16Error err) Text
forall a b. (a -> b) -> a -> b
$ Text -> Base16Error err
forall e. Text -> Base16Error e
DecodeError Text
de
    Right ByteString
a -> (err -> Base16Error err)
-> Either err Text -> Either (Base16Error err) Text
forall a b c. (a -> b) -> Either a c -> Either b c
forall (p :: * -> * -> *) a b c.
Bifunctor p =>
(a -> b) -> p a c -> p b c
first err -> Base16Error err
forall e. e -> Base16Error e
ConversionError (Either err Text -> Either (Base16Error err) Text)
-> Either err Text -> Either (Base16Error err) Text
forall a b. (a -> b) -> a -> b
$ ByteString -> Either err Text
f ByteString
a
{-# INLINE decodeBase16With #-}

-- | Decode a Base16-encoded lazy 'Text' value leniently.
--
-- Non-hexadecimal characters and a final unpaired hex digit are ignored.
-- Valid UTF-8 sequences are preserved, including across chunk boundaries.
-- Each invalid UTF-8 byte is interpreted as its Latin-1 character (U+0000
-- through U+00FF), so malformed input does not raise Unicode exceptions.
-- Decoding remains lazy in the input chunks.
--
-- N.B.: this is not RFC 4648-compliant.
--
-- === __Examples__:
--
-- >>> decodeBase16Lenient "53756e"
-- "Sun"
--
-- >>> decodeBase16Lenient "6x6x"
-- "f"
--
decodeBase16Lenient :: Text -> Text
decodeBase16Lenient :: Text -> Text
decodeBase16Lenient = OnDecodeError -> ByteString -> Text
TL.decodeUtf8With (\String
_ -> (Word8 -> Char) -> Maybe Word8 -> Maybe Char
forall a b. (a -> b) -> Maybe a -> Maybe b
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap (Int -> Char
chr (Int -> Char) -> (Word8 -> Int) -> Word8 -> Char
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Word8 -> Int
forall a b. (Integral a, Num b) => a -> b
fromIntegral))
  (ByteString -> Text) -> (Text -> ByteString) -> Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> ByteString
B16L.decodeBase16Lenient
  (ByteString -> ByteString)
-> (Text -> ByteString) -> Text -> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase16Lenient #-}

-- | Validate an untyped Base16 value and retain its encoded representation.
--
-- Accepts even-length ASCII hexadecimal input, including upper-case and
-- mixed-case digits. Empty input is valid. The original input is preserved,
-- and errors match 'decodeBase16Untyped'.
--
-- The whole input is validated before returning 'Right', regardless of
-- chunk boundaries. The returned wrapper preserves those boundaries.
--
-- This validates the Base16 encoding, not the UTF-8 validity of its decoded
-- payload. Use 'decodeBase16With' with a checked conversion for text decoding.
--
-- === __Examples__:
--
-- >>> parseBase16 "666f6"
-- Left "invalid bytestring size"
--
-- >>> parseBase16 "666F"
-- Right "666F"
--
-- >>> fmap decodeBase16 (parseBase16 "666F")
-- Right "fo"
--
-- >>> parseBase16 "6x"
-- Left "invalid character at offset: 1"
--
-- @since 2.0
--
parseBase16 :: Text -> Either T.Text (Base16 Text)
parseBase16 :: Text -> Either Text (Base16 Text)
parseBase16 Text
bs = Text -> Base16 Text
forall a. a -> Base16 a
assertBase16 Text
bs Base16 Text
-> Either Text (Base16 ByteString) -> Either Text (Base16 Text)
forall a b. a -> Either Text b -> Either Text a
forall (f :: * -> *) a b. Functor f => a -> f b -> f a
<$ ByteString -> Either Text (Base16 ByteString)
B16L.parseBase16 (Text -> ByteString
TL.encodeUtf8 Text
bs)
{-# INLINE parseBase16 #-}